Congratulations on completing this course. You now have deep insight into the fundamentals of building AI agents. You're ready to apply your skills and pursue new opportunities to continue your learning. Before you move on, let's review your key takeaways from this course. You now know that tools help LLMs access external data and support RAG, enabling the use of the organization's or other specialized databases. Tools also help process images, audio, and video to enable vision, voice, and multimodal reasoning, manage long conversations, and connect to APIs to perform real-world actions. Embedded tool calling improves LLM accuracy and reduces hallucinations by centralizing tool handling within a dedicated library or framework, replacing error-prone client-side implementations. Tools help LLMs select the correct function by briefly describing their purpose, defining the expected output, and showing the required input and output formats. Agents select a step-by-step reasoning loop that selects a tool, calls the tool, reviews the result answer, feeds the result into the process, and repeats the process as needed until the LLM and tools produce a final response. The Zero-Shot React agent uses zero-shot reasoning to solve tasks it hasn't seen before and works best for simple or well-structured problems. When building an agent in LangChain, choose an LLM that supports tool use and complex reasoning, uses tools with JSON serializable inputs and outputs, and select an agent strategy that matches task complexity. LangChain lets you build flexible agents using create_react_agent to define how the agent thinks and responds. You can customize the agent's behavior by passing in your prompt templates and tool lists to control reasoning style. You can group tools such as addition, subtraction, multiplication, and division tools into a custom math toolkit, and the agent can use them to perform calculations, and use the .invoke method to simulate chat interactions, send messages to the agent, and receive structured responses. Next, review what you've learned about manual invocation. You learned that LLMs specify task parameters and suggest tools, and agents automatically invoke tools based on direction from the LLM. You know that manual invocation involves verifying inputs and outputs and adjusting actions as needed, and that manual invocation provides greater control that can help organizations enhance safety, manage costs, and deliver more accurate information. You've learned that you can analyze and visualize data by asking natural language questions to the Pandas DataFrame agent. The Pandas DataFrame agent generates Python code that directly interacts with your DataFrame, filtering, aggregating, and visualizing data based on your natural language prompts. Your DataFrame refers to the Pandas DataFrame object that you loaded or created and then passed to the LangChain Pandas agent. You also know that LCEL pattern structures workflows use the pipe operator for precise data flow. You can define prompts using templates that include variables and side {}. You can link components for sequential execution using runnable sequence, and run multiple components concurrently on the same input using runnable parallel. You simplify syntax by replacing runnable sequence with the pipe operator, and LCEL automatically converts functions and dictionaries into compatible components using type coercion. No review would be complete without examining best practices when beginning to use agents. Always start with sandboxed environments, design clear prompts, validate the LLM analysis with human expertise, and iteratively refine your queries for safe and effective AI-driven analysis. AI-powered SQL agents allow a broader range of users to access and interpret data without needing deep technical skills. To develop applications that use natural language queries with LangChain, start by creating a Python virtual environment. Then install the required libraries, such as LangChain and your LLM, launch the SQL server, and build a database connector. Once your environment is ready, you can run natural language queries using LangChain's SQL agent, which translates those queries into SQL and retrieves results from the database. With this knowledge, we encourage you to continue learning and apply this course towards an IBM Professional Certificate. Depending on your schedule and the number of courses in the program, you can complete this Professional Certificate in approximately two months. You'll find the links to the Professional Certificate and several related courses in the congratulations and next steps reading at the end of this course. We encourage you to continue practicing your new skills. We hope your new skills support your current work and enable you to advance your career. Congratulations on completing this course. We appreciate your participation in this learning journey and wish you all the best.